© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 65491
    Prev
    Next
    INDEX
    Explanations

    describing specific domains or conditions

    np_acts-logits-general · gemini-2.5-flash-lite

    describing types of variations and systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Гор
    0.45
     लिए
    0.43
    为主
    0.43
     হলে
    0.43
    膘
    0.43
    ون
    0.42
    aceut
    0.42
     одним
    0.41
    之类的
    0.41
    为
    0.41
    POSITIVE LOGITS
     Watson
    0.41
     phenomenology
    0.41
     فونیټ
    0.41
     bestow
    0.39
     emancip
    0.39
     systemat
    0.39
     surpluses
    0.39
     निर्देशों
    0.38
     plagues
    0.38
     dys
    0.38
    Activations Density 0.032%

    No Known Activations